Search Results for author: Qing Wang

Found 165 papers, 48 papers with code

DanceChat: Large Language Model-Guided Music-to-Dance Generation

no code implementations12 Jun 2025 Qing Wang, Xiaohang Yang, Yilan Dong, Naveen Raj Govindaraj, Gregory Slabaugh, Shanxin Yuan

This approach goes beyond implicit learning from music alone, enabling the model to generate dance that is both more diverse and better aligned with musical styles.

Language Modeling Language Modelling +3

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

1 code implementation6 Jun 2025 Haowei Wang, Rupeng Zhang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang

Joint-GCG's innovative unification of gradient-based attacks across retrieval and generation stages fundamentally reshapes our understanding of vulnerabilities within RAG systems.

RAG Retrieval +1

Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM

no code implementations29 May 2025 Zhaokai Sun, Li Zhang, Qing Wang, Pan Zhou, Lei Xie

Overlapping Speech Detection (OSD) aims to identify regions where multiple speakers overlap in a conversation, a critical challenge in multi-party speech processing.

Action Detection Activity Detection +1

Towards a More Generalized Approach in Open Relation Extraction

1 code implementation28 May 2025 Qing Wang, Yuepei Li, Qiao Qiao, Kang Zhou, Qi Li

In this paper, we propose a generalized OpenRE setting that considers unlabeled data as a mixture of both known and novel instances.

Clustering Relation +1

AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery

1 code implementation27 May 2025 Haowei Wang, Junjie Wang, Xiaojun Jia, Rupeng Zhang, Mingyang Li, Zhe Liu, Yang Liu, Qing Wang

In this paper, we propose AdInject, a novel and real-world black-box attack method that leverages the internet advertising delivery to inject malicious content into the Web Agent's environment.

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

no code implementations15 May 2025 Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses.

RAG Retrieval +1

scDrugMap: Benchmarking Large Foundation Models for Drug Response Prediction

1 code implementation8 May 2025 Qing Wang, Yining Pan, Minghao Zhou, Zijia Tang, Yanfei Wang, Guangyu Wang, Qianqian Song

In the pooled-data scenario, scFoundation achieved the best performance, with mean F1 scores of 0. 971 (layer freezing) and 0. 947 (fine-tuning), outperforming the lowest-performing model by over 50%.

Benchmarking Drug Response Prediction +2

LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning

1 code implementation28 Apr 2025 Biqing Duan, Qing Wang, Di Liu, Wei Zhou, Zhenli He, Shengfa Miao

During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead.

Incremental Learning

Improving Significant Wave Height Prediction Using Chronos Models

no code implementations23 Apr 2025 Yilin Zhai, Hongyuan Shi, Chao Zhan, Qing Wang, Zaijin You, Nan Wang

Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling.

Computational Efficiency Language Modeling +3

The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report

3 code implementations14 Apr 2025 Bin Ren, Hang Guo, Lei Sun, Zongwei Wu, Radu Timofte, Yawei Li, Yao Zhang, Xinning Chai, Zhengxue Cheng, Yingsheng Qin, Yucai Yang, Li Song, Hongyuan Yu, Pufan Xu, Cheng Wan, Zhijuan Huang, Peng Guo, Shuyuan Cui, Chenjun Li, Xuehai Hu, Pan Pan, Xin Zhang, Heng Zhang, Qing Luo, Linyan Jiang, Haibo Lei, Qifang Gao, Yaqing Li, Weihua Luo, Tsing Li, Qing Wang, Yi Liu, Yang Wang, Hongyu An, Liou Zhang, Shijie Zhao, Lianhong Song, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Jing Wei, Mengyang Wang, Ruilong Guo, Qian Wang, Qingliang Liu, Yang Cheng, Davinci, Enxuan Gu, Pinxin Liu, Yongsheng Yu, Hang Hua, Yunlong Tang, Shihao Wang, ZhiYu Zhang, Yukun Yang, Jiyu Wu, Jiancheng Huang, Yifan Liu, Yi Huang, Shifeng Chen, Rui Chen, Yi Feng, Mingxi Li, Cailu Wan, XiangJi Wu, Zibin Liu, Jinyang Zhong, Kihwan Yoon, Ganzorig Gankhuyag, Shengyun Zhong, Mingyang Wu, Renjie Li, Yushen Zuo, Zhengzhong Tu, Zongang Gao, Guannan Chen, Yuan Tian, Wenhui Chen, Weijun Yuan, Zhan Li, Yihang Chen, Yifan Deng, Ruting Deng, Yilin Zhang, Huan Zheng, Yanyan Wei, Wenxuan Zhao, Suiyi Zhao, Fei Wang, Kun Li, Yinggan Tang, Mengjie Su, Jae-Hyeon Lee, Dong-Hyeop Son, Ui-Jin Choi, Tiancheng Shao, Yuqing Zhang, Mengcheng Ma, Donggeun Ko, Youngsang Kwak, Jiun Lee, Jaehwa Kwak, YuXuan Jiang, Qiang Zhu, Siyue Teng, Fan Zhang, Shuyuan Zhu, Bing Zeng, David Bull, Jing Hu, Hui Deng, Xuan Zhang, Lin Zhu, Qinrui Fan, Weijian Deng, Junnan Wu, Wenqin Deng, Yuquan Liu, Zhaohong Xu, Jameer Babu Pinjari, Kuldeep Purohit, Zeyu Xiao, Zhuoyuan Li, Surya Vashisth, Akshay Dudhane, Praful Hambarde, Sachin Chaudhary, Satya Naryan Tazi, Prashant Patil, Santosh Kumar Vipparthi, Subrahmanyam Murala, Wei-Chen Shen, I-Hsiang Chen, Yunzhe Xu, Chen Zhao, Zhizhou Chen, Akram Khatami-Rizi, Ahmad Mahmoudi-Aznaveh, Alejandro Merino, Bruno Longarela, Javier Abad, Marcos V. Conde, Simone Bianco, Luca Cogo, Gianmarco Corti

This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR).

Super-Resolution valid

PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery

no code implementations26 Feb 2025 Bo Li, Bob Zhang, Chengyang Zhang, Minghao Zhou, Weiliang Huang, Shihang Wang, Qing Wang, Mengran Li, Yong Zhang, Qianqian Song

PhenoProfiler is designed as an end-to-end tool that processes whole-slide multi-channel images directly into low-dimensional quantitative representations, eliminating the extensive computational steps required by existing methods.

Drug Discovery Representation Learning

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System

no code implementations17 Feb 2025 Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang

Inspired by the concept of mimicking the familiar, AutoCMD is capable of inferring the information utilized by upstream tools in the toolchain through learning on open-source systems and reinforcement with target system examples, thereby generating more targeted commands for information theft.

Comment Generation Large Language Model

Divergence-Augmented Policy Optimization

1 code implementation NeurIPS 2019 Qing Wang, Yingru Li, Jiechao Xiong, Tong Zhang

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data.

Atari Games Deep Reinforcement Learning +2

An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation

no code implementations18 Jan 2025 Yuxuan Dong, Qing Wang, Hengyi Hong, Ya Jiang, Shi Cheng

In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall short of providing full spatial information about the sound source.

Event Detection Sound Event Detection +1

Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning

no code implementations20 Dec 2024 Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Jun Hu, Qing Wang, Fanjiang Xu

Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance.

counterfactual Counterfactual Reasoning

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context

no code implementations17 Dec 2024 Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Qing Wang, Yihao Huang, Yang Liu

Incorporating external knowledge into large language models (LLMs) has emerged as a promising approach to mitigate outdated knowledge and hallucination in LLMs.

Hallucination Misinformation +2

DeepSN: A Sheaf Neural Framework for Influence Maximization

no code implementations16 Dec 2024 Asela Hevapathige, Qing Wang, Ahad N. Zehmakan

They have developed methods to learn the underlying diffusion processes in a data-driven manner, which enhances the generalizability of the solution, and have designed optimization objectives to identify the optimal seed set.

Marketing

Asymmetric Learning for Spectral Graph Neural Networks

1 code implementation16 Dec 2024 Fangbing Liu, Qing Wang

Extensive experiments on eighteen benchmark datasets show that asymmetric learning consistently improves the performance of spectral GNNs for both heterophilic and homophilic graphs.

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection

1 code implementation13 Dec 2024 Haowei Wang, Rupeng Zhang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang

To fill this gap, we present ToolCommander, a novel framework designed to exploit vulnerabilities in LLM tool-calling systems through adversarial tool injection.

Language Modeling Language Modelling +2

Style3D: Attention-guided Multi-view Style Transfer for 3D Object Generation

no code implementations4 Dec 2024 Bingjie Song, Xin Huang, Ruting Xie, Xue Wang, Qing Wang

Specifically, the query features from the content image preserve geometric consistency across multiple views, while the key and value features from the style image are used to guide the stylistic transfer.

3D Reconstruction Computational Efficiency +1

User-Movement-Robust Virtual Reality Through Dual-Beam Reception in mmWave Networks

no code implementations4 Dec 2024 Rizqi Hersyandika, Qing Wang, Yang Miao, Sofie Pollin

Evaluation using actual HMD movement data demonstrates the effectiveness of our approach, showcasing a reduction in outage rates of up to 13% compared to quasi-omnidirectional reception with two serving APs, and a 17% decrease compared to steerable single-beam reception with a serving AP.

Diversity

Material Anything: Generating Materials for Any 3D Object via Diffusion

no code implementations CVPR 2025 Xin Huang, Tengfei Wang, Ziwei Liu, Qing Wang

We present Material Anything, a fully-automated, unified diffusion framework designed to generate physically-based materials for 3D objects.

CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields

no code implementations21 Nov 2024 Xin-Yang Liu, Meet Hemant Parikh, Xiantao Fan, Pan Du, Qing Wang, Yi-fan Chen, Jian-Xun Wang

Eddy-resolving turbulence simulations require stochastic inflow conditions that accurately replicate the complex, multi-scale structures of turbulence.

MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation

1 code implementation21 Nov 2024 Hengyi Hong, Qing Wang, Jun Du, Ruoyu Wei, Mingqi Cai, Xin Fang

We propose a novel output representation that combines the DOA with distance of sound sources by calculating the real Cartesian coordinates to address the newly introduced source distance estimation (SDE) task in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2024 Challenge.

Data Augmentation Sound Event Localization and Detection

Bridge: A Unified Framework to Knowledge Graph Completion via Language Models and Knowledge Representation

no code implementations11 Nov 2024 Qiao Qiao, Yuepei Li, Qing Wang, Kang Zhou, Qi Li

Furthermore, to bridge the gap between KGs and PLMs, we employ a self-supervised representation learning method called BYOL to fine-tune PLMs with two different views of a triple.

Representation Learning

STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing

no code implementations1 Nov 2024 Jiaru Zou, Qing Wang, Pratyush Thakur, Nickvash Kani

Advances in large language models (LLMs) have spurred research into enhancing their reasoning capabilities, particularly in math-rich STEM documents.

2k In-Context Learning +2

CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification

no code implementations26 Oct 2024 Fangwen Mu, Junjie Wang, Zhuohao Yu, Lin Shi, Song Wang, Mingyang Li, Qing Wang

In this study, we propose CodePurify, a novel defense against backdoor attacks on code models through entropy-based purification.

Learning Partial Graph Matching via Optimal Partial Transport

no code implementations22 Oct 2024 Gathika Ratnayaka, James Nichols, Qing Wang

While recent studies have explored deep learning techniques for partial graph matching, a significant limitation remains: the absence of an optimization objective that fully captures the problem's intrinsic nature while enabling efficient solutions.

Graph Matching

Towards Bridging Generalization and Expressivity of Graph Neural Networks

no code implementations14 Oct 2024 Shouheng Li, Floris Geerts, Dongwoo Kim, Qing Wang

Expressivity and generalization are two critical aspects of graph neural networks (GNNs).

The USTC-NERCSLIP Systems for the CHiME-8 MMCSG Challenge

no code implementations8 Oct 2024 Ya Jiang, Hongbo Lan, Jun Du, Qing Wang, Shutong Niu

In the two-person conversation scenario with one wearing smart glasses, transcribing and displaying the speaker's content in real-time is an intriguing application, providing a priori information for subsequent tasks such as translation and comprehension.

speech-recognition Speech Recognition

From Prohibition to Adoption: How Hong Kong Universities Are Navigating ChatGPT in Academic Workflows

no code implementations2 Oct 2024 Junjun Huang, Jifan Wu, Qing Wang, Kemeng Yuan, Jiefeng Li, Di Lu

This paper aims at comparing the time when Hong Kong universities used to ban ChatGPT to the current periods where it has become integrated in the academic processes.

See then Tell: Enhancing Key Information Extraction with Vision Grounding

no code implementations29 Sep 2024 Shuhang Liu, Zhenrong Zhang, Pengfei Hu, Jiefeng Ma, Jun Du, Qing Wang, Jianshu Zhang, Chenyu Liu

Positioned at the outset of the answer text, the <see> token allows the model to first see--observing the regions of the image related to the input question--and then tell--providing articulated textual responses.

Image to text Key Information Extraction +4

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

no code implementations17 Sep 2024 Yuepei Li, Kang Zhou, Qiao Qiao, Bach Nguyen, Qing Wang, Qi Li

In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence.

Natural Questions RAG +2

NPU-NTU System for Voice Privacy 2024 Challenge

no code implementations6 Sep 2024 Jixun Yao, Nikita Kuzmin, Qing Wang, Pengcheng Guo, Ziqian Ning, Dake Guo, Kong Aik Lee, Eng-Siong Chng, Lei Xie

Our system employs a disentangled neural codec architecture and a serial disentanglement strategy to gradually disentangle the global speaker identity and time-variant linguistic content and paralinguistic information.

Disentanglement Speaker anonymization

PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code

no code implementations16 Aug 2024 Ziyou Jiang, Lin Shi, Guowei Yang, Qing Wang

In such cases, providing examples of insecure code and the corresponding patches would benefit the security developers to better locate and fix the insecure code.

MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement

no code implementations16 Jul 2024 Jixun Yao, Qing Wang, Pengcheng Guo, Ziqian Ning, Yuguang Yang, Yu Pan, Lei Xie

Meanwhile, we propose a straightforward anonymization strategy that employs empty embedding with zero values to simulate the speaker identity concealment process, eliminating the need for conversion to a pseudo-speaker identity and thereby reducing the complexity of speaker anonymization process.

Disentanglement Speaker anonymization

Enhancing Terrestrial Net Primary Productivity Estimation with EXP-CASA: A Novel Light Use Efficiency Model Approach

no code implementations28 Jun 2024 Guanzhou Chen, Kaiqi Zhang, Xiaodong Zhang, Hong Xie, Haobo Yang, Xiaoliang Tan, Tong Wang, Yule Ma, Qing Wang, Jinzhou Cao, Weihong Cui

The EXP-CASA model effectively improves the CASA model by using novel functions for estimating the fraction of absorbed photosynthetically active radiation (FPAR) and environmental stress, by utilizing long-term observational data from FLUXNET and MODIS surface reflectance data.

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement

1 code implementation24 Jun 2024 Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu

The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt.

Image Generation

SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding

no code implementations13 Jun 2024 Jiefeng Ma, Yan Wang, Chenyu Liu, Jun Du, Yu Hu, Zhenrong Zhang, Pengfei Hu, Qing Wang, Jianshu Zhang

Accurately identifying and organizing textual content is crucial for the automation of document processing in the field of form understanding.

Form Relation Prediction

A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition

1 code implementation27 May 2024 Zilu Guo, Qing Wang, Jun Du, Jia Pan, Qing-Feng Liu, Chin-Hui

In this paper, we propose a variance-preserving interpolation framework to improve diffusion models for single-channel speech enhancement (SE) and automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Distinctive and Natural Speaker Anonymization via Singular Value Transformation-assisted Matrix

no code implementations17 May 2024 Jixun Yao, Qing Wang, Pengcheng Guo, Ziqian Ning, Lei Xie

To address these issues and especially generate more natural and distinctive anonymized speech, we propose a novel speaker anonymization approach that models a matrix related to speaker identity and transforms it into an anonymized singular value transformation-assisted matrix to conceal the original speaker identity.

Speaker anonymization Speaker Verification

The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report

3 code implementations16 Apr 2024 Bin Ren, Nancy Mehta, Radu Timofte, Hongyuan Yu, Cheng Wan, Yuxin Hong, Bingnan Han, Zhuoyuan Wu, Yajun Zou, Yuqing Liu, Jizhe Li, Keji He, Chao Fan, Heng Zhang, Xiaolin Zhang, Xuanwu Yin, Kunlong Zuo, Bohao Liao, Peizhe Xia, Long Peng, Zhibo Du, Xin Di, Wangkai Li, Yang Wang, Wei Zhai, Renjing Pei, Jiaming Guo, Songcen Xu, Yang Cao, ZhengJun Zha, Yan Wang, Yi Liu, Qing Wang, Gang Zhang, Liou Zhang, Shijie Zhao, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Xin Liu, Min Yan, Menghan Zhou, Yiqiang Yan, Yixuan Liu, Wensong Chan, Dehua Tang, Dong Zhou, Li Wang, Lu Tian, Barsoum Emad, Bohan Jia, Junbo Qiao, Yunshuai Zhou, Yun Zhang, Wei Li, Shaohui Lin, Shenglong Zhou, Binbin Chen, Jincheng Liao, Suiyi Zhao, Zhao Zhang, Bo wang, Yan Luo, Yanyan Wei, Feng Li, Mingshen Wang, Yawei Li, Jinhan Guan, Dehua Hu, Jiawei Yu, Qisheng Xu, Tao Sun, Long Lan, Kele Xu, Xin Lin, Jingtong Yue, Lehan Yang, Shiyi Du, Lu Qi, Chao Ren, Zeyu Han, YuHan Wang, Chaolin Chen, Haobo Li, Mingjun Zheng, Zhongbao Yang, Lianhong Song, Xingzhuo Yan, Minghan Fu, Jingyi Zhang, Baiang Li, Qi Zhu, Xiaogang Xu, Dan Guo, Chunle Guo, Jiadi Chen, Huanhuan Long, Chunjiang Duanmu, Xiaoyan Lei, Jie Liu, Weilin Jia, Weifeng Cao, Wenlong Zhang, Yanyu Mao, Ruilong Guo, Nihao Zhang, Qian Wang, Manoj Pandey, Maksym Chernozhukov, Giang Le, Shuli Cheng, Hongyuan Wang, Ziyan Wei, Qingting Tang, Liejun Wang, Yongming Li, Yanhui Guo, Hao Xu, Akram Khatami-Rizi, Ahmad Mahmoudi-Aznaveh, Chih-Chung Hsu, Chia-Ming Lee, Yi-Shiuan Chou, Amogh Joshi, Nikhil Akalwadi, Sampada Malagi, Palani Yashaswini, Chaitra Desai, Ramesh Ashok Tabib, Ujwala Patil, Uma Mudenagudi

In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking.

Image Super-Resolution

Generalization of Graph Neural Networks through the Lens of Homomorphism

no code implementations10 Mar 2024 Shouheng Li, Dongwoo Kim, Qing Wang

In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism.

Generalization Bounds

Local Vertex Colouring Graph Neural Networks

1 code implementation10 Mar 2024 Shouheng Li, Dongwoo Kim, Qing Wang

Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL.

VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing

1 code implementation5 Mar 2024 Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Qing Wang

Visual entailment (VE) is a multimodal reasoning task consisting of image-sentence pairs whereby a promise is defined by an image, and a hypothesis is described by a sentence.

Multimodal Reasoning Sentence +1

Adversarial Testing for Visual Grounding via Image-Aware Property Reduction

no code implementations2 Mar 2024 Zhiyuan Chang, Mingyang Li, Junjie Wang, Cheng Li, Boyu Wu, Fanjiang Xu, Qing Wang

To this end, we propose PEELING, a text perturbation approach via image-aware property reduction for adversarial testing of the VG model.

Visual Grounding

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues

no code implementations14 Feb 2024 Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

With the development of LLMs, the security threats of LLMs are getting more and more attention.

SNP-S3: Shared Network Pre-training and Significant Semantic Strengthening for Various Video-Text Tasks

1 code implementation31 Jan 2024 Xingning Dong, Qingpei Guo, Tian Gan, Qing Wang, Jianlong Wu, Xiangyuan Ren, Yuan Cheng, Wei Chu

By employing one shared BERT-type network to refine textual and cross-modal features simultaneously, SNP is lightweight and could support various downstream applications.

Sentence

Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition

no code implementations13 Jan 2024 Hefeng Wu, Guangzhi Ye, Ziyang Zhou, Ling Tian, Qing Wang, Liang Lin

Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes.

Hallucination Novel Concepts +1

Uplifting the Expressive Power of Graph Neural Networks through Graph Partitioning

no code implementations14 Dec 2023 Asela Hevapathige, Qing Wang

In this work, we study the expressive power of graph neural networks through the lens of graph partitioning.

graph partitioning

Large Language Models are Complex Table Parsers

no code implementations13 Dec 2023 Bowen Zhao, Changkai Ji, Yuejie Zhang, Wen He, Yingwen Wang, Qing Wang, Rui Feng, Xiaobo Zhang

With the Generative Pre-trained Transformer 3. 5 (GPT-3. 5) exhibiting remarkable reasoning and comprehension abilities in Natural Language Processing (NLP), most Question Answering (QA) research has primarily centered around general QA tasks based on GPT, neglecting the specific challenges posed by Complex Table QA.

Logical Reasoning Question Answering

Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs

1 code implementation1 Dec 2023 Qing Wang, Kang Zhou, Qiao Qiao, Yuepei Li, Qi Li

We also identify the limitation of noise-contrastive estimation (NCE) loss for relation representation learning and propose to apply margin loss for sentence pairs.

Contrastive Learning Diversity +4

CoRec: An Easy Approach for Coordination Recognition

1 code implementation30 Nov 2023 Qing Wang, Haojie Jia, Wenfei Song, Qi Li

In this paper, we observe and address the challenges of the coordination recognition task.

Sentence

HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation

no code implementations CVPR 2024 Xin Huang, Ruizhi Shao, Qi Zhang, Hongwen Zhang, Ying Feng, Yebin Liu, Qing Wang

The main idea is to enhance the model's 2D perception of 3D geometry by learning a normal-adapted diffusion model and a normal-aligned diffusion model.

3D geometry Text to 3D +1

PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System

no code implementations28 Sep 2023 Xiang Lyu, Yuhang Cao, Qing Wang, JingJing Yin, Yuguang Yang, Pengpeng Zou, Yanni Hu, Heng Lu

Speaker-attributed automatic speech recognition (SA-ASR) improves the accuracy and applicability of multi-speaker ASR systems in real-world scenarios by assigning speaker labels to transcribed texts.

Action Detection Activity Detection +3

MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo

1 code implementation23 Sep 2023 Rongxuan Tan, Qing Wang, Xueyan Wang, Chao Yan, Yang Sun, Youyang Feng

We design a multi-scale windows PatchMatch (mPM) to obtain reliable depth of untextured areas.

3D Reconstruction

Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval

no code implementations20 Sep 2023 Chen Jiang, Kaiming Huang, Sifeng He, Xudong Yang, Wei zhang, Xiaobo Zhang, Yuan Cheng, Lei Yang, Qing Wang, Furong Xu, Tan Pan, Wei Chu

SSAN is based on two newly proposed modules in video retrieval: (1) An efficient Self-supervised Keyframe Extraction (SKE) module to reduce redundant frame features, (2) A robust Similarity Pattern Detection (SPD) module for temporal alignment.

Retrieval Video Retrieval

Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning

1 code implementation20 Sep 2023 Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi

We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.

Contrastive Learning Retrieval +4

How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection

4 code implementations25 Aug 2023 Yiyang Yao, Peng Liu, Tiancheng Zhao, Qianqian Zhang, Jiajia Liao, Chunxin Fang, Kyusong Lee, Qing Wang

Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research.

Object Detection

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks

no code implementations17 Aug 2023 Junkai Qian, Yuning Jiang, Xin Liu, Qing Wang, Ting Wang, Yuanming Shi, Wei Chen

To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed.

Deep Reinforcement Learning reinforcement-learning

Inverting the Imaging Process by Learning an Implicit Camera Model

no code implementations CVPR 2023 Xin Huang, Qi Zhang, Ying Feng, Hongdong Li, Qing Wang

In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.

Multi-agent Policy Reciprocity with Theoretical Guarantee

no code implementations12 Apr 2023 Haozhi Wang, Yinchuan Li, Qing Wang, Yunfeng Shao, Jianye Hao

We then define an adjacency space for mismatched states and design a plug-and-play module for value iteration, which enables agents to infer more precise returns.

continuous-control Continuous Control +2

N-WL: A New Hierarchy of Expressivity for Graph Neural Networks

no code implementations The Eleventh International Conference on Learning Representations 2023 Qing Wang, Dillon Chen, Asiri Wijesinghe, Shouheng Li, Muhammad Farhan

The expressive power of Graph Neural Networks (GNNs) is fundamental for understanding their capabilities and limitations, i. e., what graph properties can or cannot be learnt by a GNN.

Wide-Angle Rectification via Content-Aware Conformal Mapping

no code implementations CVPR 2023 Qi Zhang, Hongdong Li, Qing Wang

Despite the proliferation of ultra wide-angle lenses on smartphone cameras, such lenses often come with severe image distortion (e. g. curved linear structure, unnaturally skewed faces).

CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset

1 code implementation CVPR 2023 Tian Gan, Qing Wang, Xingning Dong, Xiangyuan Ren, Liqiang Nie, Qingpei Guo

Though there are certain methods studying the Chinese video-text pre-training, they pre-train their models on private datasets whose videos and text are unavailable.

A Unified Object Counting Network with Object Occupation Prior

1 code implementation29 Dec 2022 Shengqin Jiang, Qing Wang, Fengna Cheng, Yuankai Qi, Qingshan Liu

In this paper, we build the first evolving object counting dataset and propose a unified object counting network as the first attempt to address this task.

Crowd Counting Knowledge Distillation +2

Performance Evaluation, Optimization and Dynamic Decision in Blockchain Systems: A Recent Overview

no code implementations29 Nov 2022 Quan-Lin Li, Yan-Xia Chang, Qing Wang

We believe that the basic theory with mathematical methods, algorithms and simulations of blockchain systems discussed in this paper will strongly support future development and continuous innovation of blockchain technology.

Deep Reinforcement Learning Federated Learning

A SVD-based Dynamic Harmonic Phasor Estimator with Improved Suppression of Out-of-Band Interference

no code implementations16 Nov 2022 Dongfang Zhao, Shisong Li, Fuping Wang, Wei Zhao, Songling Huang, Qing Wang

The diffusion of nonlinear loads and power electronic devices in power systems deteriorates the signal environment and increases the difficulty of measuring harmonic phasors.

Preserving background sound in noise-robust voice conversion via multi-task learning

no code implementations6 Nov 2022 Jixun Yao, Yi Lei, Qing Wang, Pengcheng Guo, Ziqian Ning, Lei Xie, Hai Li, Junhui Liu, Danming Xie

Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios.

Multi-Task Learning Voice Conversion

Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency Scaling

no code implementations6 Nov 2022 Jixun Yao, Qing Wang, Yi Lei, Pengcheng Guo, Lei Xie, Namin Wang, Jie Liu

By directly scaling the formant and F0, the speaker distinguishability degradation of the anonymized speech caused by the introduction of other speakers is prevented.

Speaker anonymization Speaker Verification

TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge

no code implementations26 Oct 2022 Bowen Pang, Huan Zhao, Gaosheng Zhang, Xiaoyue Yang, Yang Sun, Li Zhang, Qing Wang, Lei Xie

In this challenge, we explore three kinds of typical speaker diarization systems, which are spectral clustering(SC) based diarization, target-speaker voice activity detection(TS-VAD) and end-to-end neural diarization(EEND) respectively.

Action Detection Activity Detection +2

Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function

no code implementations26 Oct 2022 Qing Wang, Hang Chen, Ya Jiang, Zhe Wang, Yuyang Wang, Jun Du, Chin-Hui Lee

In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function.

Active Speaker Detection Sound Source Localization

NWPU-ASLP System for the VoicePrivacy 2022 Challenge

no code implementations24 Sep 2022 Jixun Yao, Qing Wang, Li Zhang, Pengcheng Guo, Yuhao Liang, Lei Xie

Our system consists of four modules, including feature extractor, acoustic model, anonymization module, and neural vocoder.

Speaker anonymization Speaker Verification

On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies

no code implementations21 Sep 2022 Haozhi Wang, Qing Wang, Yunfeng Shao, Dong Li, Jianye Hao, Yinchuan Li

Modern meta-reinforcement learning (Meta-RL) methods are mainly developed based on model-agnostic meta-learning, which performs policy gradient steps across tasks to maximize policy performance.

continuous-control Continuous Control +5

Automatic Comment Generation via Multi-Pass Deliberation

1 code implementation14 Sep 2022 Fangwen Mu, Xiao Chen, Lin Shi, Song Wang, Qing Wang

Then, we treat the comment of the retrieved code as the initial draft and input it with the code and keywords into DECOM to start the iterative deliberation process.

Articles Comment Generation

Tensor Decomposition based Personalized Federated Learning

no code implementations27 Aug 2022 Qing Wang, Jing Jin, Xiaofeng Liu, Huixuan Zong, Yunfeng Shao, Yinchuan Li

Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data.

Diversity Model Optimization +2

Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering

no code implementations6 Jun 2022 Shouheng Li, Dongwoo Kim, Qing Wang

While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs.

Clustering Node Classification

Epipolar Focus Spectrum: A Novel Light Field Representation and Application in Dense-view Reconstruction

no code implementations1 Apr 2022 Yaning Li, Xue Wang, Hao Zhu, Guoqing Zhou, Qing Wang

Existing light field representations, such as epipolar plane image (EPI) and sub-aperture images, do not consider the structural characteristics across the views, so they usually require additional disparity and spatial structure cues for follow-up tasks.

CardioID: Mitigating the Effects of Irregular Cardiac Signals for Biometric Identification

no code implementations30 Mar 2022 Weizheng Wang, Marco Zuniga, Qing Wang

In this work, we analyze cardiac signals collected in more realistic (uncontrolled) scenarios and show that their high signal variability (i. e., irregularity) makes it harder to obtain stable and distinct user features.

Sparse Federated Learning with Hierarchical Personalized Models

no code implementations25 Mar 2022 Xiaofeng Liu, Qing Wang, Yunfeng Shao, Yinchuan Li

To this end, we propose a personalized FL algorithm using a hierarchical proximal mapping based on the moreau envelop, named sparse federated learning with hierarchical personalized models (sFedHP), which significantly improves the global model performance facing diverse data.

Autonomous Vehicles Federated Learning

MatchFormer: Interleaving Attention in Transformers for Feature Matching

1 code implementation17 Mar 2022 Qing Wang, Jiaming Zhang, Kailun Yang, Kunyu Peng, Rainer Stiefelhagen

While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline, fail to make use of the matching capacity of the encoder and tend to overburden the decoder for matching.

Decoder Homography Estimation +2

Knowledge Tracing: A Survey

no code implementations8 Jan 2022 Ghodai Abdelrahman, Qing Wang, Bernardo Pereira Nunes

A human teacher can track the knowledge of students to customize the teaching on students needs.

Knowledge Tracing Survey

Fast and Unsupervised Action Boundary Detection for Action Segmentation

no code implementations CVPR 2022 Zexing Du, Xue Wang, Guoqing Zhou, Qing Wang

To deal with the great number of untrimmed videos produced every day, we propose an efficient unsupervised action segmentation method by detecting boundaries, named action boundary detection (ABD).

Boundary Detection Change Point Detection +1

Deep Open Set Identification for RF Devices

no code implementations5 Dec 2021 Qing Wang, Qing Liu, Zihao Zhang, HaoYu Fang, Xi Zheng

Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process.

SIDNet: Learning Shading-aware Illumination Descriptor for Image Harmonization

no code implementations2 Dec 2021 Zhongyun Hu, Ntumba Elie Nsampi, Xue Wang, Qing Wang

Before solving these two sub-problems, we first learn a shading-aware illumination descriptor via a well-designed neural rendering framework, of which the key is a shading bases module that generates multiple shading bases from the foreground image.

Image Harmonization Neural Rendering

HDR-NeRF: High Dynamic Range Neural Radiance Fields

1 code implementation CVPR 2022 Xin Huang, Qi Zhang, Ying Feng, Hongdong Li, Xuan Wang, Qing Wang

The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.

NeRF Novel View Synthesis +1

Learning Data Teaching Strategies Via Knowledge Tracing

no code implementations13 Nov 2021 Ghodai Abdelrahman, Qing Wang

In this paper, we propose a novel method, called Knowledge Augmented Data Teaching (KADT), which can optimize a data teaching strategy for a student model by tracing its knowledge progress over multiple learning concepts in a learning task.

image-classification Image Classification +3

A Regularized Wasserstein Framework for Graph Kernels

1 code implementation6 Oct 2021 Asiri Wijesinghe, Qing Wang, Stephen Gould

This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which can preserve both features and structure of graphs via Wasserstein distances on features and their local variations, local barycenters and global connectivity.

A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?"

1 code implementation ICLR 2022 Asiri Wijesinghe, Qing Wang

To elaborate this framework, we propose a novel neural model, called GraphSNN, and prove that this model is strictly more expressive than the Weisfeiler Lehman test in distinguishing graph structures.

Graph Learning

Multiple Intelligent Reflecting Surface aided Multi-user Weighted Sum-Rate Maximization using Manifold Optimization

no code implementations29 Sep 2021 Liyue Zhang, Qing Wang, Haozhi Wang

Intelligent reflecting surface (IRS) are able to amend radio propagation condition tasks on account of its functional properties in phase shift optimizing.

Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing

no code implementations18 Aug 2021 Ghodai Abdelrahman, Qing Wang

Further, this model has the capability of learning relationships between latent concepts from a dynamic latent concept graph in light of a student's evolving knowledge states.

Knowledge Tracing

VTLayout: Fusion of Visual and Text Features for Document Layout Analysis

no code implementations12 Aug 2021 Shoubin Li, Xuyan Ma, Shuaiqun Pan, Jun Hu, Lin Shi, Qing Wang

In the second stage, the deep visual, shallow visual, and text features are extracted for fusion to identify the category blocks of documents.

Document Layout Analysis

Structured Directional Pruning via Perturbation Orthogonal Projection

no code implementations12 Jul 2021 Yinchuan Li, Xiaofeng Liu, Yunfeng Shao, Qing Wang, Yanhui Geng

Structured pruning is an effective compression technique to reduce the computation of neural networks, which is usually achieved by adding perturbations to reduce network parameters at the cost of slightly increasing training loss.

Sparse Personalized Federated Learning

1 code implementation12 Jul 2021 Xiaofeng Liu, Yinchuan Li, Qing Wang, Xu Zhang, Yunfeng Shao, Yanhui Geng

By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with non-sparse FL.

Diversity Personalized Federated Learning

The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems

no code implementations1 Jul 2021 Qing Wang

In today's business marketplace, many high-tech Internet enterprises constantly explore innovative ways to provide optimal online user experiences for gaining competitive advantages.

Interactive Recommendation

Episode Adaptive Embedding Networks for Few-shot Learning

1 code implementation17 Jun 2021 Fangbing Liu, Qing Wang

Few-shot learning aims to learn a classifier using a few labelled instances for each class.

Few-Shot Learning Metric Learning

Pose2Drone: A Skeleton-Pose-based Framework for Human-Drone Interaction

1 code implementation27 May 2021 Zdravko Marinov, Stanka Vasileva, Qing Wang, Constantin Seibold, Jiaming Zhang, Rainer Stiefelhagen

Our framework provides the functionality to control the movement of the drone with simple arm gestures and to follow the user while keeping a safe distance.

Pose Estimation

Explore BiLSTM-CRF-Based Models for Open Relation Extraction

no code implementations26 Apr 2021 Tao Ni, Qing Wang, Gabriela Ferraro

Extracting multiple relations from text sentences is still a challenge for current Open Relation Extraction (Open RE) tasks.

Relation Relation Extraction

Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

no code implementations26 Mar 2021 Sean Li, Dongwoo Kim, Qing Wang

The proposed model is shown to generalize well to both homophilic and heterophilic graphs.

Node Classification

FIXME: Enhance Software Reliability with Hybrid Approaches in Cloud

no code implementations17 Feb 2021 Jinho Hwang, Larisa Shwartz, Qing Wang, Raghav Batta, Harshit Kumar, Michael Nidd

The process of continuous integration/deployment (CICD) in cloud connects developers who need to deliver value faster and more transparently with site reliability engineers (SREs) who need to manage applications reliably.

Machine learning accelerated computational fluid dynamics

1 code implementation28 Jan 2021 Dmitrii Kochkov, Jamie A. Smith, Ayya Alieva, Qing Wang, Michael P. Brenner, Stephan Hoyer

Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics and plasma physics.

BIG-bench Machine Learning

Deep Anti-aliasing of Whole Focal Stack Using Slice Spectrum

no code implementations23 Jan 2021 Yaning Li, Xue Wang, Hao Zhu, Guoqing Zhou, Qing Wang

Based on these two observations, we propose a learning-based FSS reconstruction approach for one-time aliasing removing over the whole focal stack.

Depth Estimation

Chiral effective Lagrangian for excited heavy-light mesons from QCD

no code implementations18 Jan 2021 Qing-Sen Chen, Hui-Feng Fu, Yong-Liang Ma, Qing Wang

We derive the chiral effective Lagrangian for excited heavy-light mesons from QCD under proper approximations.

High Energy Physics - Phenomenology

Global Node Attentions via Adaptive Spectral Filters

no code implementations1 Jan 2021 Shouheng Li, Dongwoo Kim, Qing Wang

The proposed model has been shown to generalize well to both assortative and disassortative graphs.

Node Classification

ErGAN: Generative Adversarial Networks for Entity Resolution

no code implementations18 Dec 2020 Jingyu Shao, Qing Wang, Asiri Wijesinghe, Erhard Rahm

Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets.

Diversity Entity Resolution +1

Chiral effective Lagrangian for heavy-light mesons from QCD: $1/m_{Q}$ correction

no code implementations7 Dec 2020 Qing-Sen Chen, Hui-Feng Fu, Yong-Liang Ma, Qing Wang

The low energy constants in the effective Lagrangian are expressed in terms of the light quark self-energy and heavy quark mass $m_Q$.

High Energy Physics - Phenomenology

Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning

1 code implementation13 Nov 2020 Xuehui Wang, Qing Wang, Yuzhi Zhao, Junchi Yan, Lei Fan, Long Chen

In this paper, we develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$^2$F) for SISR.

Image Super-Resolution

Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain

no code implementations8 Nov 2020 Koen Oostermeijer, Qing Wang, Jun Du

One of the strengths of traditional convolutional neural networks (CNNs) is their inherent translational invariance.

Speech Enhancement

PEL-BERT: A Joint Model for Protocol Entity Linking

no code implementations28 Jan 2020 Shoubin Li, Wenzao Cui, Yujiang Liu, Xuran Ming, Jun Hu, YuanzheHu, Qing Wang

Pre-trained models such as BERT are widely used in NLP tasks and are fine-tuned to improve the performance of various NLP tasks consistently.

Descriptive Entity Linking +2

Knowledge Tracing with Sequential Key-Value Memory Networks

1 code implementation29 Oct 2019 Ghodai Abdelrahman, Qing Wang

Although these deep learning models have shown promising results, they have limitations: either lack the ability to go deeper to trace how specific concepts in a knowledge state are mastered by a student, or fail to capture long-term dependencies in an exercise sequence.

Deep Learning Knowledge Tracing +1

DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters

1 code implementation NeurIPS 2019 Asiri Wijesinghe, Qing Wang

We propose a novel spectral convolutional neural network (CNN) model on graph structured data, namely Distributed Feedback-Looped Networks (DFNets).

Document Classification General Classification +1

Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning

no code implementations10 Sep 2019 Liheng Chen, Hongyi Guo, Yali Du, Fei Fang, Haifeng Zhang, Yaoming Zhu, Ming Zhou, Wei-Nan Zhang, Qing Wang, Yong Yu

Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the non-stationary problem in training, their decentralized execution paradigm limits the agents' capability to coordinate.

Multi-agent Reinforcement Learning reinforcement-learning +2

Learning to Sample: an Active Learning Framework

no code implementations9 Sep 2019 Jingyu Shao, Qing Wang, Fangbing Liu

However, current learning-based active learning approaches still require sufficient training data so as to generalize meta-learning models for active learning.

Active Learning Diversity +4

Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction

no code implementations15 May 2019 Lingbo Liu, Zhilin Qiu, Guanbin Li, Qing Wang, Wanli Ouyang, Liang Lin

Finally, a GCC module is applied to model the correlation between all regions by computing a global correlation feature as a weighted sum of all regional features, with the weights being calculated as the similarity between the corresponding region pairs.

Prediction

Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition

no code implementations22 Apr 2019 Guanbin Li, Xin Zhu, Yirui Zeng, Qing Wang, Liang Lin

Specifically, by analyzing the symbiosis and mutual exclusion of AUs in various facial expressions, we organize the facial AUs in the form of structured knowledge-graph and integrate a Gated Graph Neural Network (GGNN) in a multi-scale CNN framework to propagate node information through the graph for generating enhanced AU representation.

Facial Action Unit Detection Graph Neural Network +1

Robust Visual Tracking Using Dynamic Classifier Selection with Sparse Representation of Label Noise

no code implementations19 Mar 2019 Yuefeng Chen, Qing Wang

However, the self-updating scheme makes these methods suffer from drifting problem because of the incorrect labels of weak classifiers in training samples.

Visual Tracking

Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane Images

no code implementations15 Feb 2019 Hao Zhu, Mantang Guo, Hongdong Li, Qing Wang, Antonio Robles-Kelly

We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.

Super-Resolution

Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning

no code implementations10 Dec 2018 Lingbo Liu, Guanbin Li, Yuan Xie, Yizhou Yu, Qing Wang, Liang Lin

In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.

Face Alignment Face Detection +2

TStarBots: Defeating the Cheating Level Builtin AI in StarCraft II in the Full Game

2 code implementations19 Sep 2018 Peng Sun, Xinghai Sun, Lei Han, Jiechao Xiong, Qing Wang, Bo Li, Yang Zheng, Ji Liu, Yongsheng Liu, Han Liu, Tong Zhang

Both TStarBot1 and TStarBot2 are able to defeat the built-in AI agents from level 1 to level 10 in a full game (1v1 Zerg-vs-Zerg game on the AbyssalReef map), noting that level 8, level 9, and level 10 are cheating agents with unfair advantages such as full vision on the whole map and resource harvest boosting.

AI Agent Decision Making +3

A Generic Multi-Projection-Center Model and Calibration Method for Light Field Cameras

no code implementations7 Aug 2018 Qi Zhang, Chunping Zhang, Jinbo Ling, Qing Wang, Jingyi Yu

Based on the MPC model and projective transformation, we propose a calibration algorithm to verify our light field camera model.

3D geometry 3D Reconstruction

End-to-end driving simulation via angle branched network

no code implementations19 May 2018 Qing Wang, Long Chen, Wei Tian

Imitation learning for end-to-end autonomous driving has drawn attention from academic communities.

Autonomous Driving Imitation Learning +1

Light Field Segmentation From Super-pixel Graph Representation

no code implementations20 Dec 2017 Xianqiang Lv, Hao Zhu, Qing Wang

The large volume of input data and the redundancy of light field make it an open challenge.

Segmentation

MTNA: A Neural Multi-task Model for Aspect Category Classification and Aspect Term Extraction On Restaurant Reviews

no code implementations IJCNLP 2017 Wei Xue, Wubai Zhou, Tao Li, Qing Wang

Online reviews are valuable resources not only for consumers to make decisions before purchase, but also for providers to get feedbacks for their services or commodities.

Aspect-Based Sentiment Analysis Extract Aspect +5

Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms

no code implementations10 Aug 2017 Qing Wang, Chunqiu Zeng, Wubai Zhou, Tao Li, Larisa Shwartz, Genady Ya. Grabarnik

To address these issues, collaborative filtering (CF), one of the recommendation techniques relying on the interaction data only, as well as the online multi-armed bandit mechanisms, capable of achieving the balance between exploitation and exploration, are adopted in the online interactive recommendation settings, by assuming independent items (i. e., arms).

Articles Collaborative Filtering +1

4D Light Field Superpixel and Segmentation

no code implementations CVPR 2017 Hao Zhu, Qi Zhang, Qing Wang

Superpixel segmentation of 2D image has been widely used in many computer vision tasks.

Segmentation

Collective Vertex Classification Using Recursive Neural Network

no code implementations24 Jan 2017 Qiongkai Xu, Qing Wang, Chenchen Xu, Lizhen Qu

In this paper, we propose a graph-based recursive neural network framework for collective vertex classification.

Classification General Classification

Towards Evidence-Based Ontology for Supporting Systematic Literature Review

no code implementations22 Sep 2016 Yueming Sun, Ye Yang, He Zhang, Wen Zhang, Qing Wang

[Conclusions]: The approach of using ontology could effectively and efficiently support the conducting of systematic literature review.

Systematic Literature Review

Discovering and Deciphering Relationships Across Disparate Data Modalities

4 code implementations16 Sep 2016 Joshua T. Vogelstein, Eric Bridgeford, Qing Wang, Carey E. Priebe, Mauro Maggioni, Cencheng Shen

Understanding the relationships between different properties of data, such as whether a connectome or genome has information about disease status, is becoming increasingly important in modern biological datasets.

Computational Efficiency

Unconstrained Two-parallel-plane Model for Focused Plenoptic Cameras Calibration

no code implementations16 Aug 2016 Chunping Zhang, Zhe Ji, Qing Wang

The geometry of the recovered scene structure is affected by the calibration of the plenoptic camera significantly.

3D Reconstruction Vocal Bursts Valence Prediction

DARI: Distance metric And Representation Integration for Person Verification

no code implementations15 Apr 2016 Guangrun Wang, Liang Lin, Shengyong Ding, Ya Li, Qing Wang

The past decade has witnessed the rapid development of feature representation learning and distance metric learning, whereas the two steps are often discussed separately.

Ranked #7 on Person Re-Identification on SYSU-30k (using extra training data)

Metric Learning Person Re-Identification +2

Data-Driven Scene Understanding with Adaptively Retrieved Exemplars

no code implementations3 Feb 2015 Xionghao Liu, Wei Yang, Liang Lin, Qing Wang, Zhaoquan Cai, Jian-Huang Lai

In the first step, the references are selected by jointly matching their appearances with the target as well as the semantics (i. e. the assigned labels of the target and the references).

Scene Understanding Semantic Segmentation +1

Aliasing Detection and Reduction in Plenoptic Imaging

no code implementations CVPR 2014 Zhaolin Xiao, Qing Wang, Guoqing Zhou, Jingyi Yu

When using plenoptic camera for digital refocusing, angular undersampling can cause severe (angular) aliasing artifacts.

Demosaicking

Cannot find the paper you are looking for? You can Submit a new open access paper.